Invariance to microphone array configuration is a rare attribute in neural beamformers. Filter-and-sum (FS) methods in this class define the target signal with respect to a reference channel. However, this not only complicates formulation in reverberant conditions but also the network, which must have a mechanism to infer what the reference channel is. To address these issues, this study presents Delay Filter-and-Sum Network (DFSNet), a steerable neural beamformer invariant to microphone number and array geometry for causal speech enhancement. In DFSNet, acquired signals are first steered toward the speech source direction prior to the FS operation, which simplifies the task into the estimation of delay-and-summed reverberant clean speech. The proposed model is designed to incur low latency, distortion, and memory and computational burden, giving rise to high potential in hearing aid applications. Simulation results reveal comparable performance to noncausal state-of-the-art.
翻译:移动式麦克风阵列配置在神经波束变异中是一个罕见的属性。 本类的过滤和总和(FS)方法定义了一个引用频道的目标信号。 但是,这不仅使反应状态下的配方复杂化,而且使网络复杂化,因为网络必须有一个机制来推断引用频道是什么。 为解决这些问题,本研究展示了延迟过滤和合成网络(DFSNet),这是一个可控神经链,对麦克风号码和阵列几何测量功能不起作用,以便增强因果语音。在DFSNet中,获得的信号首先在FS操作之前被引导到语音源方向,从而简化了任务,以估计延迟和缓冲变动的清洁讲话。拟议模型的设计是为了产生低的耐用性、扭曲、记忆和计算负担,从而产生听力援助应用程序的高度潜力。模拟结果显示,其性能与非致癌状态相当。</s>